We present a method for identifying groups of test examples -- slices -- on
which a model under-performs, a task now known as slice discovery. We formalize
coherence -- a requirement that erroneous predictions, within a slice, should
be wrong for the same reason -- as a key property that any slice discovery
method should satisfy. We then use influence functions to derive a new slice
discovery method, InfEmbed, which satisfies coherence by returning slices whose
examples are influenced similarly by the training data. InfEmbed is simple, and
consists of applying K-Means clustering to a novel representation we deem
influence embeddings. We show InfEmbed outperforms current state-of-the-art
methods on 2 benchmarks, and is effective for model debugging across several
case studies.

我们提出了一种识别测试例组的方法 —— 切片发现。我们将一致性定义为切片发现方法应该满足的一个关键属性，即同一切片内的错误预测应该有相同的原因。然后我们使用影响函数来推导一种新的切片发现方法 InfEmbed，它通过返回示例受相似训练数据影响的切片来满足一致性。InfEmbed 简单易用，通过将 K-Means 聚类应用于我们称为影响嵌入的新型表示方法。我们在两个基准测试中展示了 InfEmbed 的优越性，并且通过几个案例研究证明了其在模型调试中的有效性。